skip to main content

Title: A High Performance Content Based Recommender System Using Hypernym Expansion

There are two major limitations in content-based recommender systems, the first is accurately measuring the similarity of preferred documents to a large set of general documents, and the second is over-specialization which limits the "interesting" documents recommended from a general document set. To address these issues, we propose combining linguistic methods and term frequency methods to improve overall performance and recommendation.
Publication Date:
OSTI Identifier:
Report Number(s):
Hypernym; 004919WKSTN00
DOE Contract Number:
Resource Type:
Software Revision:
Software Package Number:
Software CPU:
Source Code Available:
Research Org:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org:
Contributing Orgs:
Thomas E. Potok and Robert M. Patton
Country of Publication:
United States

To initiate an order for this software, request consultation services, or receive further information, fill out the request form below. You may also reach us by email at: .

OSTI staff will begin to process an order for scientific and technical software once the payment and signed site license agreement are received. If the forms are not in order, OSTI will contact you. No further action will be taken until all required information and/or payment is received. Orders are usually processed within three to five business days.

Software Request